Shell's HPC Evolution - Accelerating Seismic Processing with AWS GPU Innovation
AWS Events via YouTube
-
23
-
- Write review
Learn EDR Internals: Research & Development From The Masters
Learn Generative AI, Prompt Engineering, and LLMs for Free
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
Discover Shell's transformative journey in hybrid high-performance computing through this 42-minute conference talk from AWS re:Invent 2025. Explore how Shell revolutionized their seismic processing and AI applications by combining on-premises systems with AWS GPU capabilities, achieving remarkable 3-5x project acceleration while maintaining cost efficiency. Learn about the critical evolution from CPU-based processing to advanced GPU implementations that represents a significant advancement in energy sector computing. Examine the technical details of migrating Shell's processing code to AWS, implementing GPU-based Full-Waveform Inversion workflows, and achieving substantial cost reductions in non-EC2 services. Gain valuable insights into the latest developments in capacity block services, transitions to H200 GPUs, and understand the future landscape of energy sector HPC through Amazon Parallel Computing Service and Energy HPC Orchestrator platforms. Understand how this hybrid approach delivers both performance improvements and cost optimization for complex computational workloads in the energy industry.
Syllabus
AWS re:Invent 2025 - Shell's HPC Evolution: Accelerating Seismic Processing with AWS GPU Innovation
Taught by
AWS Events